From 08aaeda3970c778c5bb612c416a04ece38f807cb Mon Sep 17 00:00:00 2001 From: Antonio Ramirez Date: Fri, 27 Dec 2013 18:06:27 +0100 Subject: [PATCH] refactored inflector's slug and improved fallback char map --- framework/CHANGELOG.md | 2 +- framework/yii/helpers/BaseInflector.php | 86 +++++++++++++++++++++++--- tests/unit/framework/helpers/InflectorTest.php | 2 + 3 files changed, 80 insertions(+), 10 deletions(-) diff --git a/framework/CHANGELOG.md b/framework/CHANGELOG.md index b5e60a4..c2f9761 100644 --- a/framework/CHANGELOG.md +++ b/framework/CHANGELOG.md @@ -41,7 +41,7 @@ Yii Framework 2 Change Log - Chg: Changed the signature of `urlCreator` and button creators for `yii\gridview\ActionColumn` (qiangxue) - New #1438: [MongoDB integration](https://github.com/yiisoft/yii2-mongodb) ActiveRecord and Query (klimov-paul) - New #1393: [Codeception testing framework integration](https://github.com/yiisoft/yii2-codeception) (Ragazzo) -- Enh #364: Added `TransliteratorHelper` (tonydspaniard) +- Enh #364: Improve Inflector::slug with `intl` transliteration. Improved transliteration char map. (tonydspaniard) 2.0.0 alpha, December 1, 2013 --------------------------- diff --git a/framework/yii/helpers/BaseInflector.php b/framework/yii/helpers/BaseInflector.php index cb6a1dc..4886d22 100644 --- a/framework/yii/helpers/BaseInflector.php +++ b/framework/yii/helpers/BaseInflector.php @@ -217,6 +217,68 @@ class BaseInflector ]; /** + * @var array map of special chars and its translation. This is used by [[slug()]]. + */ + public static $transliteration = [ + // Latin + 'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', 'Æ' => 'AE', 'Ç' => 'C', + 'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I', 'Ï' => 'I', + 'Ð' => 'D', 'Ñ' => 'N', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' => 'O', 'Ő' => 'O', + 'Ø' => 'O', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'Ű' => 'U', 'Ý' => 'Y', 'Þ' => 'TH', + 'ß' => 'ss', + 'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' => 'a', 'å' => 'a', 'æ' => 'ae', 'ç' => 'c', + 'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e', 'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', + 'ð' => 'd', 'ñ' => 'n', 'ò' => 'o', 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o', 'ő' => 'o', + 'ø' => 'o', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'u', 'ű' => 'u', 'ý' => 'y', 'þ' => 'th', + 'ÿ' => 'y', + // Latin symbols + '©' => '(c)', + // Greek + 'Α' => 'A', 'Β' => 'B', 'Γ' => 'G', 'Δ' => 'D', 'Ε' => 'E', 'Ζ' => 'Z', 'Η' => 'H', 'Θ' => '8', + 'Ι' => 'I', 'Κ' => 'K', 'Λ' => 'L', 'Μ' => 'M', 'Ν' => 'N', 'Ξ' => '3', 'Ο' => 'O', 'Π' => 'P', + 'Ρ' => 'R', 'Σ' => 'S', 'Τ' => 'T', 'Υ' => 'Y', 'Φ' => 'F', 'Χ' => 'X', 'Ψ' => 'PS', 'Ω' => 'W', + 'Ά' => 'A', 'Έ' => 'E', 'Ί' => 'I', 'Ό' => 'O', 'Ύ' => 'Y', 'Ή' => 'H', 'Ώ' => 'W', 'Ϊ' => 'I', + 'Ϋ' => 'Y', + 'α' => 'a', 'β' => 'b', 'γ' => 'g', 'δ' => 'd', 'ε' => 'e', 'ζ' => 'z', 'η' => 'h', 'θ' => '8', + 'ι' => 'i', 'κ' => 'k', 'λ' => 'l', 'μ' => 'm', 'ν' => 'n', 'ξ' => '3', 'ο' => 'o', 'π' => 'p', + 'ρ' => 'r', 'σ' => 's', 'τ' => 't', 'υ' => 'y', 'φ' => 'f', 'χ' => 'x', 'ψ' => 'ps', 'ω' => 'w', + 'ά' => 'a', 'έ' => 'e', 'ί' => 'i', 'ό' => 'o', 'ύ' => 'y', 'ή' => 'h', 'ώ' => 'w', 'ς' => 's', + 'ϊ' => 'i', 'ΰ' => 'y', 'ϋ' => 'y', 'ΐ' => 'i', + // Turkish + 'Ş' => 'S', 'İ' => 'I', 'Ç' => 'C', 'Ü' => 'U', 'Ö' => 'O', 'Ğ' => 'G', + 'ş' => 's', 'ı' => 'i', 'ç' => 'c', 'ü' => 'u', 'ö' => 'o', 'ğ' => 'g', + // Russian + 'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', 'Е' => 'E', 'Ё' => 'Yo', 'Ж' => 'Zh', + 'З' => 'Z', 'И' => 'I', 'Й' => 'J', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N', 'О' => 'O', + 'П' => 'P', 'Р' => 'R', 'С' => 'S', 'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'H', 'Ц' => 'C', + 'Ч' => 'Ch', 'Ш' => 'Sh', 'Щ' => 'Sh', 'Ъ' => '', 'Ы' => 'Y', 'Ь' => '', 'Э' => 'E', 'Ю' => 'Yu', + 'Я' => 'Ya', + 'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd', 'е' => 'e', 'ё' => 'yo', 'ж' => 'zh', + 'з' => 'z', 'и' => 'i', 'й' => 'j', 'к' => 'k', 'л' => 'l', 'м' => 'm', 'н' => 'n', 'о' => 'o', + 'п' => 'p', 'р' => 'r', 'с' => 's', 'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'h', 'ц' => 'c', + 'ч' => 'ch', 'ш' => 'sh', 'щ' => 'sh', 'ъ' => '', 'ы' => 'y', 'ь' => '', 'э' => 'e', 'ю' => 'yu', + 'я' => 'ya', + // Ukrainian + 'Є' => 'Ye', 'І' => 'I', 'Ї' => 'Yi', 'Ґ' => 'G', + 'є' => 'ye', 'і' => 'i', 'ї' => 'yi', 'ґ' => 'g', + // Czech + 'Č' => 'C', 'Ď' => 'D', 'Ě' => 'E', 'Ň' => 'N', 'Ř' => 'R', 'Š' => 'S', 'Ť' => 'T', 'Ů' => 'U', + 'Ž' => 'Z', + 'č' => 'c', 'ď' => 'd', 'ě' => 'e', 'ň' => 'n', 'ř' => 'r', 'š' => 's', 'ť' => 't', 'ů' => 'u', + 'ž' => 'z', + // Polish + 'Ą' => 'A', 'Ć' => 'C', 'Ę' => 'e', 'Ł' => 'L', 'Ń' => 'N', 'Ó' => 'o', 'Ś' => 'S', 'Ź' => 'Z', + 'Ż' => 'Z', + 'ą' => 'a', 'ć' => 'c', 'ę' => 'e', 'ł' => 'l', 'ń' => 'n', 'ó' => 'o', 'ś' => 's', 'ź' => 'z', + 'ż' => 'z', + // Latvian + 'Ā' => 'A', 'Č' => 'C', 'Ē' => 'E', 'Ģ' => 'G', 'Ī' => 'i', 'Ķ' => 'k', 'Ļ' => 'L', 'Ņ' => 'N', + 'Š' => 'S', 'Ū' => 'u', 'Ž' => 'Z', + 'ā' => 'a', 'č' => 'c', 'ē' => 'e', 'ģ' => 'g', 'ī' => 'i', 'ķ' => 'k', 'ļ' => 'l', 'ņ' => 'n', + 'š' => 's', 'ū' => 'u', 'ž' => 'z' + ]; + + /** * Converts a word to its plural form. * Note that this is for English only! * For example, 'apple' will become 'apples', and 'child' will become 'children'. @@ -379,20 +441,26 @@ class BaseInflector /** * Returns a string with all spaces converted to given replacement and * non word characters removed. Maps special characters to ASCII using - * [[TransliteratorHelper::process()]] + * [[$transliteration]] array. * @param string $string An arbitrary string to convert * @param string $replacement The replacement to use for spaces + * @param bool $lowercase * @return string The converted string. */ - public static function slug($string, $replacement = '-') + public static function slug($string, $replacement = '-', $lowercase = true) { - $map = array( - '/[^\w\s]/' => ' ', - '/\\s+/' => $replacement, - '/(?<=[a-z])([A-Z])/' => $replacement . '\\1', - str_replace(':rep', preg_quote($replacement, '/'), '/^[:rep]+|[:rep]+$/') => '' - ); - return preg_replace(array_keys($map), array_values($map), TransliteratorHelper::process($string, '', 'en')); + // ensure UTF-8 and remove invalid UTF-8 chars. + $string = mb_convert_encoding((string) $string, 'UTF-8', mb_list_encodings()); + if (extension_loaded('intl') === true) { + $options = 'Any-Latin; NFD; [:Nonspacing Mark:] Remove; NFC; [:Punctuation:] Remove;'; + $string = transliterator_transliterate($options, $string); + $string = preg_replace('/[-\s]+/', $replacement, $string); + } else { + $string = str_replace(array_keys(static::$transliteration), static::$transliteration, $string); + $string = preg_replace('/[^\p{L}\p{Nd}]+/u', $replacement, $string); + } + $string = trim($string, $replacement); + return $lowercase ? strtolower($string) : $string; } /** diff --git a/tests/unit/framework/helpers/InflectorTest.php b/tests/unit/framework/helpers/InflectorTest.php index 2cd3c9f..e303ebd 100644 --- a/tests/unit/framework/helpers/InflectorTest.php +++ b/tests/unit/framework/helpers/InflectorTest.php @@ -123,6 +123,8 @@ class InflectorTest extends TestCase public function testSlug() { + $this->assertEquals("privet-hello-jii-framework-kak-dela-how-it-goes", Inflector::slug('Привет Hello Йии-- Framework !--- Как дела ? How it goes ?')); + $this->assertEquals("this-is-a-title", Inflector::slug('this is a title')); }